The Role of Medication Data to Enhance the Prediction of Alzheimer’s Progression Using Machine Learning

Table 2

The performance for the AD vs. pMCI vs sMCI task.

		Testing performance				Cross-validation performance
Model	Dataset	A		R	F1	A		R	F1
RF	CS	87.76	87.76	87.79	87.76	90.35  2.9	90.49  2.8	90.47  2.7	90.28  2.5
	AM	68.05	67.47	68.82	68.05	58.39  4.1	58.3  4.26	60.74  4.3	58.27  4.2
	AM-CS	88.54	88.51	88.92	88.54	92.74  3.1	92.87  3.1	93.03  2.6	93.21  3.3
DT	CS	90.89	90.94	91.15	90.89	83.08  4.9	83.08  4.9	83.49  4.9	83.13  4.8
	AM	64.81	64.64	69.15	64.81	53.23  4.3	53.23  4.6	55.27  4.7	53.21  4.2
	AM-CS	89.32	89.30	89.74	89.32	84.96  3.7	84.95  3.7	85.61  3.5	85.15  3.7
LR	CS	76.85	77.15	78.34	76.85	79.85  4.4	79.96  4.3	80.61  4.2	79.85  4.4
	AM	53.24	51.32	52.76	53.24	55.39  4.6	54.64  4.6	54.7  4.71	55.39  4.6
	AM-CS	85.42	85.40	85.64	85.42	88.40  3.3	88.36  3.3	88.91  3.1	88.4  3.28
SVM	CS	81.02	81.11	81.40	81.02	79.95  3.9	79.93  4.0	80.7  3.96	79.95  3.9
	AM	58.33	57.05	58.85	58.33	55.35  4.5	55.52  4.4	56.54  4.3	55.35  4.5
	AM-CS	76.39	76.55	77.04	76.39	82.89  3.1	82.78  3.1	83.18  3.1	82.89  3.1
KNN	CS	73.61	74.31	76.53	73.61	76.32  3.7	76.8  3.68	80.52  3.4	76.32  3.7
	AM	48.00	42.67	45.20	48.00	52.31  3.2	43.13  3.4	39.62  7.5	52.31  3.2
	AM-CS	74.22	72.37	82.99	74.22	82.43  4.2	82.11  4.4	84.62  3.8	82.43  4.2